Finding mr and mrs entity in the city of knowledge

Abstract

More and more urban data is published every day, and consequently, consumers want to take advantage of this body of knowledge. Unfortunately, metadata and schema information around this content is sparse. To effectively fulfill user information needs, systems must be able to capture user intent and context in order to evolve beyond current search and exploration techniques. A Linked Data approach is uniquely positioned to surface information and provide interoperability across a diversity of information sources, from consumer data residing in the original enterprise systems, to relevant open city data in tabular form. We present a prototype for contextual knowledge mining that enables federated access and querying of entities across hundreds of enterprise and open datasets pertaining to cities. The proposed system is able to (1) lift raw tabular data into a connected and meaningful structure, contextualized within the Web of Data, and (2) support novel search and exploration tasks, by identifying closely related entities across datasets and models. Our user experiments and prototype show how semantics, used to consolidate city information and reuse assets from the Web of Data, improve dataset search and provide users effective means to explore related entities and content to fit their information needs. © 2014 ACM.